The rain hammered against the windows, a steady, rhythmic drumming. Maria sat on the sofa, wrapped in a warm blanket, a book resting on her lap. She’d spent the day indoors, contentedly observing the world from the sheltered confines of her home. Her movements were slow, her thoughts meandering.

While sorting through a box of old papers, she discovered a letter she’d written to her estranged sister, a plea for reconciliation. It was a reminder of a past that weighed on her. She re-read the words, a deep sense of acceptance enveloping her. Time, she realized, had softened the edges of her grief. She smiled and placed the letter in a special place.

Emotion: patient

Cluster: Passivity
PC1 (Valence): 2.71 Positive
PC2 (Disposition): 0.40

Role in Research

This story is one of 1,000 stories generated for the emotion patient. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 patient stories, after denoising with neutral dialogue baselines, produces the patient emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the patient vector is projected through the unembedding matrix.

Promoted:
rest0.467
eventually0.415
leisurely0.369
慢慢0.357
a0.355
Suppressed:
无法-0.432
even-0.428
인해-0.421
無法-0.415
😣-0.391